CarbonLot
An MCP-native compliance agent for the EU's Carbon Border Adjustment Mechanism (CBAM), enabling natural-language queries to validate shipments, calculate embedded emissions, and generate CBAM declarations.
README
CarbonLot 🌍
An MCP-native compliance agent for the EU's Carbon Border Adjustment Mechanism (CBAM).
Since January 2026, Indian steel, aluminium, and other CBAM-covered exporters must report verified embedded carbon emissions per shipment to the EU — or get charged a punitive default rate. That data currently lives scattered across shipment records, supplier declarations, and emission-factor tables, making it slow and error-prone to check compliance manually.
CarbonLot fixes this by treating carbon like a traceability problem, not a spreadsheet problem. Ask it "is shipment SHP001 CBAM-ready?" and it looks up the shipment's supplier, checks whether they've reported verified emissions data, falls back transparently to EU default values when they haven't, calculates the total embedded emissions, and drafts a ready-to-use CBAM declaration — all through natural conversation via MCP.
Built for the Manufacturing & Industry 4.0 Track — MCP Hackathon 2026.
Tech Stack
- NitroStack (MCP SDK + CLI)
- TypeScript
- Zod (schema validation)
- MCP Resources, Tools
What It Does
- 🔍 Validates CN codes — checks whether a shipment's product code falls within CBAM's regulatory scope
- 📊 Looks up emission sources — checks if the shipment's supplier has reported verified emissions, or if EU default values apply
- 🧮 Calculates embedded emissions — computes total CO₂e per shipment using verified supplier data where available
- 🚩 Flags fallback cases transparently — shipments with unregistered/unreported suppliers are explicitly marked as needing review, not silently defaulted
- 📄 Generates CBAM declarations — auto-drafts a structured compliance document per shipment, ready for export documentation
Project structure
src/
├── data/
│ ├── shipments.json # Shipment records (CN code, quantity, supplier, origin)
│ ├── suppliers.json # Supplier-reported emissions, pricing, delivery data
│ └── emission_factors.json # EU CBAM default emission factors by CN code
├── modules/
│ └── carbon/
│ ├── carbon.tools.ts # validate_cn_code, lookup_emission_factor,
│ │ # calculate_emissions, generate_declaration
│ ├── carbon.resources.ts # Exposes shipments/suppliers/emission-factors as MCP resources
│ └── carbon.module.ts # Registers the carbon module
├── app.module.ts # Root application module
└── index.ts
MCP Architecture
Resources (data the agent can read):
data://shipments— shipment recordsdata://suppliers— supplier-reported emissions datadata://emission-factors— CBAM default emission factors per CN code
Tools (actions the agent can perform):
validate_cn_code(shipmentId)— checks if a shipment's product falls under CBAM scopelookup_emission_factor(shipmentId)— determines whether verified supplier data or EU defaults applycalculate_emissions(shipmentId)— computes total embedded emissions (kg CO2e)generate_declaration(shipmentId)— builds the final CBAM compliance declaration
Getting Started
npm install npm run dev
Then connect via NitroStudio or your preferred MCP client, and try asking:
"Is shipment SHP001 CBAM ready?"
Honest Note on Scope
The emissions and supplier dataset used here is a realistic, hand-modelled sample (not a live ERP/ ecosystem integration) — built to demonstrate the full compliance-agent workflow end-to-end within the hackathon timeframe. Emission factor values should be verified against official CBAM implementing regulation tables before any real-world use.
Team
Built for MCP Hackathon 2026 by:
- N Samiksha
- Krishna Jayakumar
- Kashyap S
- Muhanned Jasimkhan JL
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。